Layout and context understanding for image synthesis with scene graphs
Advancements on text-to-image synthesis generate remarkable images from textual descriptions. However, these methods are designed to generate only one object with varying attributes. They face difficulties with complex descriptions having multiple arbitrary objects since it would require information...
Saved in:
Main Authors: | , , , |
---|---|
Format: | text |
Published: |
Animo Repository
2019
|
Subjects: | |
Online Access: | https://animorepository.dlsu.edu.ph/faculty_research/3355 |
Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
Institution: | De La Salle University |
id |
oai:animorepository.dlsu.edu.ph:faculty_research-4357 |
---|---|
record_format |
eprints |
spelling |
oai:animorepository.dlsu.edu.ph:faculty_research-43572022-11-16T02:27:49Z Layout and context understanding for image synthesis with scene graphs Talavera, Arces Tan, Daniel Stanley Azcarraga, Arnulfo P. Hua, Kai Lung Advancements on text-to-image synthesis generate remarkable images from textual descriptions. However, these methods are designed to generate only one object with varying attributes. They face difficulties with complex descriptions having multiple arbitrary objects since it would require information on the placement and sizes of each object in the image. Recently, a method that infers object layouts from scene graphs has been proposed as a solution to this problem. However, their method uses only object labels in describing the layout, which fail to capture the appearance of some objects. Moreover, their model is biased towards generating rectangular shaped objects in the absence of ground-truth masks. In this paper, we propose an object encoding module to capture object features and use it as additional information to the image generation network. We also introduce a graph-cuts based segmentation method that can infer the masks of objects from bounding boxes to better model object shapes. Our method produces more discernible images with more realistic shapes as compared to the images generated by the current state-of-the-art method. © 2019 IEEE. 2019-09-01T07:00:00Z text text/html https://animorepository.dlsu.edu.ph/faculty_research/3355 info:doi/10.1109/ICIP.2019.8803182 Faculty Research Work Animo Repository Image analysis Computer graphics Computer Sciences |
institution |
De La Salle University |
building |
De La Salle University Library |
continent |
Asia |
country |
Philippines Philippines |
content_provider |
De La Salle University Library |
collection |
DLSU Institutional Repository |
topic |
Image analysis Computer graphics Computer Sciences |
spellingShingle |
Image analysis Computer graphics Computer Sciences Talavera, Arces Tan, Daniel Stanley Azcarraga, Arnulfo P. Hua, Kai Lung Layout and context understanding for image synthesis with scene graphs |
description |
Advancements on text-to-image synthesis generate remarkable images from textual descriptions. However, these methods are designed to generate only one object with varying attributes. They face difficulties with complex descriptions having multiple arbitrary objects since it would require information on the placement and sizes of each object in the image. Recently, a method that infers object layouts from scene graphs has been proposed as a solution to this problem. However, their method uses only object labels in describing the layout, which fail to capture the appearance of some objects. Moreover, their model is biased towards generating rectangular shaped objects in the absence of ground-truth masks. In this paper, we propose an object encoding module to capture object features and use it as additional information to the image generation network. We also introduce a graph-cuts based segmentation method that can infer the masks of objects from bounding boxes to better model object shapes. Our method produces more discernible images with more realistic shapes as compared to the images generated by the current state-of-the-art method. © 2019 IEEE. |
format |
text |
author |
Talavera, Arces Tan, Daniel Stanley Azcarraga, Arnulfo P. Hua, Kai Lung |
author_facet |
Talavera, Arces Tan, Daniel Stanley Azcarraga, Arnulfo P. Hua, Kai Lung |
author_sort |
Talavera, Arces |
title |
Layout and context understanding for image synthesis with scene graphs |
title_short |
Layout and context understanding for image synthesis with scene graphs |
title_full |
Layout and context understanding for image synthesis with scene graphs |
title_fullStr |
Layout and context understanding for image synthesis with scene graphs |
title_full_unstemmed |
Layout and context understanding for image synthesis with scene graphs |
title_sort |
layout and context understanding for image synthesis with scene graphs |
publisher |
Animo Repository |
publishDate |
2019 |
url |
https://animorepository.dlsu.edu.ph/faculty_research/3355 |
_version_ |
1767195888321560576 |